In the Industrial Internet of Things (IIoT), Protocol Reverse Engineering (PRE) is a technique that analyzes protocol message samples to facilitate the understanding of unknown protocol specifications, enabling intercommunication between heterogeneous devices using industrial control protocols (ICPs). However, capturing message samples from the IloT environment is time-consuming, and the collected samples may lack sufficient diversity to comprehensively cover the protocol specifications, thereby affecting PRE's effectiveness in understanding protocol specifications. To address this limitation, we propose a message expansion method driven by device interaction to efficiently generate message samples that offer comprehensive feature coverage, ultimately enhancing the protocol understanding. Our approach operates in two stages. During the exploration stage, it modifies the initial input messages captured from the network and, through interactions with the device, determines which fields should be excluded from further exploration, thereby narrowing the exploration space. In the expansion stage, we design a neighborhood particle swarm optimization (NPSO) algorithm to thoroughly explore the remaining search space, generating diverse messages and validating them through interaction with the device to comprehensively cover the protocol's structure and functionality. Experimental results show that our method surpasses existing algorithms in both message generation speed and message quality.

Time-Sensitive Networking (TSN), renowned for its deterministic properties, has become a pivotal technology under-pinning real-time industrial control in Cyber-Physical Systems. Existing research emphasizes enhancing the transmission services of TSN networks for control applications by improving flow schedulability and minimizing end-to-end delay. However, these studies abstract the performance requirements of control applications into rigid, impractical constraints for flow scheduling, disrupting the connection between control optimization and transmission enhancement, and eventually undermining genuine progress in industrial control. Within a co-optimization framework of communication and control, this paper proposes AFS-RT, an Adaptive TSN Flow Scheduling method for Robotic arm Teleoperation, a representative industrial control application. Specifically, through a comprehensive analysis of the teleoperation case, we first integrate slot allocation-based flow scheduling with remote control to formulate a control-driven co-optimization model. To tackle the complexities arising from the implicit mapping between communication and control, we augment the Deep Reinforcement Learning agent responsible for slot allocation with slot-correlation-guided feature extraction, improving feature comprehension by leveraging inherent correlations between slots and thereby boosting the agent’s decision-making capabilities. Extensive testbed and simulation experiments demonstrate that AFS-RT significantly improves teleoperation performance under diverse network conditions compared to SOTA algorithms.